{"total":71,"rows":[{"id":"2410.12761","title":"SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation","created":"2024-10-16","cited_by_count":133,"area":"diffusion"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2407.15861","title":"Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey","created":"2024-07-10","cited_by_count":35,"area":"diffusion"},{"id":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"id":"2504.01081","title":"ShieldGemma 2: Robust and Tractable Image Content Moderation","created":"2025-04-01","cited_by_count":28,"area":null},{"id":"2505.12677","title":"CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models","created":"2025-05-19","cited_by_count":27,"area":"diffusion"},{"id":"2405.13360","title":"How to Trace Latent Generative Model Generated Images without Artificial Watermark?","created":"2024-05-22","cited_by_count":26,"area":"diffusion"},{"id":"2502.08011","title":"Training-Free Safe Denoisers for Safe Use of Diffusion Models","created":"2025-02-11","cited_by_count":21,"area":"diffusion"},{"id":"2412.10493","title":"AlignGuard: Scalable Safety Alignment for Text-to-Image Generation","created":"2024-12-13","cited_by_count":20,"area":"alignment"},{"id":"2501.03544","title":"PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models","created":"2025-01-07","cited_by_count":17,"area":"safety"},{"id":"2502.16368","title":"Concept Corrector: Erase concepts on the fly for text-to-image diffusion models","created":"2025-02-22","cited_by_count":11,"area":"diffusion"},{"id":"2410.02710","title":"SteerDiff: Steering towards Safe Text-to-Image Diffusion Models","created":"2024-10-03","cited_by_count":10,"area":"diffusion"},{"id":"2410.21471","title":"AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models","created":"2024-10-28","cited_by_count":10,"area":"diffusion"},{"id":"2505.19398","title":"Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2502.14896","title":"A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models","created":"2025-02-17","cited_by_count":9,"area":"diffusion"},{"id":"2507.16302","title":"Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning","created":"2025-07-22","cited_by_count":9,"area":"diffusion"},{"id":"2508.03696","title":"PLA: Prompt Learning Attack against Text-to-Image Generative Models","created":"2025-07-14","cited_by_count":9,"area":"safety"},{"id":"2601.10242","title":"Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?","created":"2026-01-15","cited_by_count":8,"area":null},{"id":"2412.05538","title":"Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2412.18123","title":"AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2501.18877","title":"Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models","created":"2025-01-31","cited_by_count":7,"area":"diffusion"},{"id":"2503.13994","title":"TarPro: Targeted Protection against Malicious Image Editing","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2510.24012","title":"Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models","created":"2025-10-28","cited_by_count":7,"area":"diffusion"},{"id":"2512.16625","title":"DeContext as Defense: Safe Image Editing in Diffusion Transformers","created":"2025-12-18","cited_by_count":7,"area":"diffusion"},{"id":"2503.14232","title":"CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models","created":"2025-03-18","cited_by_count":6,"area":"diffusion"},{"id":"2410.14881","title":"Class-RAG: Real-Time Content Moderation with Retrieval Augmented Generation","created":"2024-10-18","cited_by_count":5,"area":"rag"},{"id":"2412.21052","title":"Towards Effective Discrimination Testing for Generative AI","created":"2024-12-30","cited_by_count":5,"area":null},{"id":"2505.21347","title":"OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models","created":"2025-05-27","cited_by_count":5,"area":"safety"},{"id":"2411.10329","title":"Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2412.10807","title":"Towards Action Hijacking of Large Language Model-based Agent","created":"2024-12-14","cited_by_count":4,"area":"agents"},{"id":"2506.20151","title":"EAR: Erasing Concepts from Unified Autoregressive Models","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2601.00267","title":"ActErase: A Training-Free Paradigm for Precise Concept Erasure via Activation Redirection","created":"2026-01-01","cited_by_count":4,"area":"diffusion"},{"id":"2603.25994","title":"Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models","created":"2026-03-27","cited_by_count":4,"area":"diffusion"},{"id":"2509.22723","title":"Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models","created":"2025-09-25","cited_by_count":3,"area":"diffusion"},{"id":"2511.05865","title":"CGCE: Classifier-Guided Concept Erasure in Generative Models","created":"2025-11-08","cited_by_count":3,"area":"safety"},{"id":"2603.03163","title":"Conditioned Activation Transport for T2I Safety Steering","created":"2026-03-03","cited_by_count":3,"area":"mechinterp"},{"id":"2606.15608","title":"On the Adversarial Robustness of Multimodal LLM Judges","created":"2026-06-14","cited_by_count":3,"area":"mllm"},{"id":"2502.05242","title":"Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2503.00020","title":"A Systematic Review of Open Datasets Used in Text-to-Image (T2I) Gen AI Model Safety","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2507.17554","title":"An h-space Based Adversarial Attack for Protection Against Few-shot Personalization","created":"2025-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2509.21360","title":"Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models","created":"2025-09-21","cited_by_count":2,"area":"safety"},{"id":"2510.24820","title":"SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing","created":"2025-10-28","cited_by_count":2,"area":"safety"},{"id":"2511.19558","title":"SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation","created":"2025-11-24","cited_by_count":2,"area":"diffusion"},{"id":"2605.19739","title":"FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models","created":"2026-05-19","cited_by_count":2,"area":"diffusion"},{"id":"2606.05290","title":"Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2411.13982","title":"Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2411.16769","title":"Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting","created":"2024-11-25","cited_by_count":1,"area":"safety"},{"id":"2503.11742","title":"Safe Vision-Language Models via Unsafe Weights Manipulation","created":"2025-03-14","cited_by_count":1,"area":"mllm"},{"id":"2508.01151","title":"Personalized Safety Alignment for Text-to-Image Diffusion Models","created":"2025-08-02","cited_by_count":1,"area":"diffusion"},{"id":"2604.06285","title":"Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization","created":"2026-04-07","cited_by_count":1,"area":"mllm"},{"id":"2606.17257","title":"Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering","created":"2026-06-15","cited_by_count":1,"area":"diffusion"},{"id":"2606.27147","title":"Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2607.00402","title":"The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models","created":"2026-07-01","cited_by_count":1,"area":"diffusion"},{"id":"2409.17682","title":"Dark Miner: Defend against undesirable generation for text-to-image diffusion models","created":"2024-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2502.06023","title":"Dual Caption Preference Optimization for Diffusion Models","created":"2025-02-09","cited_by_count":0,"area":"diffusion"},{"id":"2511.11014","title":"SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation","created":"2025-11-14","cited_by_count":0,"area":"safety"},{"id":"2511.21180","title":"CAHS-Attack: CLIP-Aware Heuristic Search Attack Method for Stable Diffusion","created":"2025-11-26","cited_by_count":0,"area":"diffusion"},{"id":"2512.10766","title":"Metaphor-based Jailbreak Attacks on Text-to-Image Models","created":"2025-12-06","cited_by_count":0,"area":"safety"},{"id":"2602.00616","title":"SPOT: Selective Prompt Projection via Total Variation for Inference-Only Safe Text-to-Image Generation","created":"2026-01-31","cited_by_count":0,"area":"diffusion"},{"id":"2604.02265","title":"Modular Energy Steering for Safe Text-to-Image Generation with Foundation Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.06063","title":"EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.00874","title":"Latent Space Probing for Adult Content Detection in Video Generative Models","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2607.06120","title":"AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models","created":"2026-07-07","cited_by_count":0,"area":"diffusion"},{"id":"2607.14945","title":"Introspective Attention Modulation for Safe Text-to-Image Generation","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.16828","title":"UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation","created":"2026-07-18","cited_by_count":0,"area":"diffusion"},{"id":"2609.13534","title":"Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models","created":"2026-09-11","cited_by_count":0,"area":"safety"},{"id":"2609.37576","title":"Evaluating the Evaluators: Diagnosing Large Multimodal Models for AI-Generated Image Assessment","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.39688","title":"ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.02300","title":"Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05908","title":"Safe Image Generation via Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"deeprl"},{"id":"2610.19563","title":"SaTPO: Text-to-Image Safety Alignment via Transition Preference Optimization","created":"2026-10-14","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}